Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    attends to specific tokens marked with asterisks from related tokens marked with double square brackets

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.21
    1:0.41
    2:0.05
    3:0.05
    4:0.08
    5:0.03
    6:0.05
    7:0.09
    Negative Logits
    uke
    -0.57
    stata
    -0.57
     Gelb
    -0.57
     is
    -0.56
     blancs
    -0.56
    Carla
    -0.56
     bianchi
    -0.56
     الجمع
    -0.56
    zak
    -0.55
     tirage
    -0.54
    POSITIVE LOGITS
    SequentialGroup
    0.79
    $.\\
    0.75
    ieteur
    0.73
    ]));
    0.69
    }');
    0.68
    aimana
    0.68
    InjectAttribute
    0.68
    ')),
    0.67
    ]))
    0.67
    thenburg
    0.66
    Act Density 5.122%

    No Known Activations